mlsanityData to 7 Oct 2026

On Episodes, Prototypical Networks, and Few-shot Learning

arXiv 2012.09831 ↗First posted 17 Dec 2020cs.LG cs.CVcited by 46

Not on the map. Why?

Abstract (arXiv)

Episodic learning is a popular practice among researchers and practitioners interested in few-shot learning. It consists of organising training in a series of learning problems (or episodes), each divided into a small training and validation subset to mimic the circumstances encountered during evaluation. But is this always necessary? In this paper, we investigate the usefulness of episodic learning in methods which use nonparametric approaches, such as nearest neighbours, at the level of the episode. For these methods, we not only show how the constraints imposed by episodic learning are not necessary, but that they in fact lead to a data-inefficient way of exploiting training batches. We conduct a wide range of ablative experiments with Matching and Prototypical Networks, two of the most popular methods that use nonparametric approaches at the level of the episode. Their "non-episodic" counterparts are considerably simpler, have less hyperparameters, and improve their performance in multiple few-shot classification datasets.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 7; 2024: 10; 2025: 5; 2026: 5.

46 papers.

Sort:

By area:

  1. 2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
  2. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 52
  3. 2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
  4. 2024Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Latercited by 28
  5. 2022Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Surveycited by 27
  6. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  7. 2023Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Modelscited by 24
  8. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  9. 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
  10. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  11. 2021Sparse Spatial Transformers for Few-Shot Learningcited by 14
  12. 2023Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variantscited by 14
34 more
  1. 2022Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classificationcited by 10
  2. 2021Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shiftcited by 9
  3. 2021Uniform Sampling over Episode Difficultycited by 6
  4. 2022Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Predictioncited by 6
  5. 2024Towards Incremental Learning in Large Language Models: A Critical Reviewcited by 6
  6. 2025INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomycited by 5
  7. 2022Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regionscited by 4
  8. 2022Adaptive Prototypical Networkscited by 4
  9. 2022A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classificationcited by 4
  10. 2023Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategiescited by 4
  11. 2024Towards Novel Malicious Packet Recognition: A Few-Shot Learning Approachcited by 4
  12. 2023Modularity in Deep Learning: A Surveycited by 3
  13. 2026Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysiscited by 3
  14. 2022Unsupervised Few-shot Learning via Deep Laplacian Eigenmapscited by 2
  15. 2022Few-shot Classification with Hypersphere Modeling of Prototypescited by 2
  16. 2024Towards Generative Class Prompt Learning for Fine-grained Visual Recognitioncited by 2
  17. 2024Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samplescited by 2
  18. 2024Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distributioncited by 1
  19. 2024PEFSL: A deployment Pipeline for Embedded Few-Shot Learning on a FPGA SoCcited by 1
  20. 2025Few-shot Hate Speech Detection Based on the MindSpore Frameworkcited by 1
  21. 2021Exploring the Limits of Natural Language Inference Based Setup for Few-Shot Intent Detectioncited by 0
  22. 2022Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learnerscited by 0
  23. 2022Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classificationcited by 0
  24. 2022Few-Shot Classification of Skin Lesions from Dermoscopic Images by Meta-Learning Representative Embeddingscited by 0
  25. 2024Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attentioncited by 0
  26. 2024Episodic-free Task Selection for Few-shot Learningcited by 0
  27. 2024Class-Incremental Few-Shot Event Detectioncited by 0
  28. 2025Geometric Mean Improves Loss For Few-Shot Learningcited by 0
  29. 2025ProtoN: Prototype Node Graph Neural Network for Unconstrained Multi-Impression Ear Recognitioncited by 0
  30. 2025Balanced Few-Shot Episodic Learning for Accurate Retinal Disease Diagnosiscited by 0
  31. 2026Contrastive Domain Generalization for Cross-Instrument Molecular Identification in Mass Spectrometrycited by 0
  32. 2026SRasP: Self-Reorientation Adversarial Style Perturbation for Cross-Domain Few-Shot Learningcited by 0
  33. 2026BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognitioncited by 0
  34. 2026Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptionscited by 0